Doktora Tezleri

Permanent URI for this collectionhttps://gcris.yasar.edu.tr/handle/123456789/13679

Browse

Browsing Doktora Tezleri by Subject "Accounting Mistakes and Frauds"

Filter results by typing the first few letters
Now showing 1 - 1 of 1
  • Thumbnail Image
    Doctoral Thesis
    Hileli finansal aktivitelerin sinir ağları algoritmaları ile öngörülmesi
    (2019) Okur, Mustafa Reha; Karaibrahimoğlu, Yasemin; Yeşilova, Fatma Dilvin Taşkın
    Despite worldwide regulatory efforts (e.g., Sarbanes – Oxley Act, Financial Security Law of France, Fraud Act 2006 of the United Kingdom), fraud is still a major concern of today's capital markets. This study aims to forecast the risk of fraudulent financial activities of cross-listed companies in US stock exchanges (NYSE, NASDAQ) by employing a Neural Network based algorithm. Data of financial fraud filings, financial statements, corporate governance variables, and macroeconomic indicators are collected to construct a comprehensive study. By this method, this study tries to develop a broader framework on fraud detection that does not focus only on firm-specific aspects, instead of covering a more comprehensive dataset, which incorporates country-specific institutional factors into consideration. This study employs four machine learning based classification algorithms. Random Forest and C4.5 algorithm outperformed others with superior classification power. Moreover, this study mostly exceeds the classification ability of the previous literature.